Modify RunONNXModel.py for pip install

[chentong319]

The goal is to create a python package so that we can run an inference like onnxruntime in python script. Since the RunONNXModel.py provides most of the necessary functionality, I added extra support in that script. The pip package related code will be checked later. I tested with a local pip install. We can upload the package later.

Major changes:

1. Add the function interface to call the main in RunONNXModel.py with the parameters similar to onnxruntime:
2. Accept list of arrays as input.
3. Return the outputs

Example:

import numpy as np
import onnxmlirrun

a = np.zeros((3,4,5), dtype=np.float32)
b = a + 4
r = onnxmlirrun.RunONNXModel.onnxmlirrun(compiled_so="/Users/chentong/Projects/onnx-mlir/build/test_add.so", inputs=[a,b])
print(r)
r = onnxmlirrun.RunONNXModel.onnxmlirrun(onnx_model="/Users/chentong/Projects/onnx-mlir/build/test_add.onnx", inputs=[a,b])
print(r)

We may have different name for the functions and the package. Comments are welcome.

[AlexandreEichenberger]

@chentong319 Can you add a reference to the ORT interface that this PR is imitating.

In your first example

r = onnxmlirrun.RunONNXModel.onnxmlirrun(compiled_so="/Users/chentong/Projects/onnx-mlir/build/test_add.so", inputs=[a,b])

was the onnx_model parameter omitted on purpose? Just for me to understand better the interface.

[chentong319]

@chentong319 Can you add a reference to the ORT interface that this PR is imitating.

In your first example

r = onnxmlirrun.RunONNXModel.onnxmlirrun(compiled_so="/Users/chentong/Projects/onnx-mlir/build/test_add.so", inputs=[a,b])

was the onnx_model parameter omitted on purpose? Just for me to understand better the interface.

Yes, onnx_model is not needed if the compiled .so is provided. By the way, the two onnxmilrrun.RunONNXModel.onnxmlirrun commands are two independent ways to do inference.

[AlexandreEichenberger]

Got it, so we can provide a onnx file or a pre-compiled binary, smart, thanks.

[tungld]

Should we check if both onnx_model and compiled_so are not given?

[AlexandreEichenberger]

Make sense, and maybe if none are given, an error?

[tungld]

onnxmlirrun.RunONNXModel.onnxmlirrun

My two cents here. For the package name (the first onnxmlirrun), just onnxmlir is enough to avoid typing two Rs.
I would remove RunONNXModel, but it seems not straightforward unless we reorganize RunONNXModel.py.

Anyway, we have several python utilities, perhaps it's time to reorganize them into a single python package.